Definition
Neuroevolution is a method for modifying neural network weights, topologies, or ensembles in order to learn a specific task. Evolutionary computation (see Evolutionary Algorithms) is used to search for network parameters that maximize a fitness function that measures performance in the task. Compared to other neural network learning methods, neuroevolution is highly general, allowing learning without explicit targets, with non differentiable activation functions, and with recurrent networks. It can also be combined with standard neural network learning, e.g. to biological adaptation. Neuroevolution can also be seen as a policy search method for reinforcement-learning problems, where it is well suited to continuous domains and to domains where the state is only partially observable.
Motivation and Background
The primary motivation for neuroevolution is to be able to train neural networks in sequential decision tasks...
Recommended Reading
Ackley, D., & Littman, M. (1992). Interactions between learning and evolution. In C. G. Langton, C. Taylor, J. D. Farmer, & S. Rasmussen (Eds.), Artificial life II (pp. 487–509). Reading, MA: Addison-Wesley.
Angeline, P. J., Saunders, G. M., & Pollack, J. B. (1994). An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5, 54–65.
Bryant, B. D., & Miikkulainen, R. (2007). Acquiring visibly intelligent behavior with example-guided neuroevolution http://nn.cs.utexas.edu/keyword?bryant:aaai07. In Proceedings of the twenty-second national conference on artificial intelligence (pp. 801–808). Menlo Park, CA: AAAI Press.
Chellapilla, K., & Fogel, D. B. (1999). Evolution, neural networks, games, and intelligence. Proceedings of the IEEE, 87, 1471–1496.
Floreano, D.,  Dürr, P., & Mattiussi, C. (2008). Neuroevolution: From architectures to learning. Evolutionary Intelligence, 1, 47–62.
Gomez, F., & Miikkulainen, R. (2003). Active guidance for a finless rocket using neuroevolution http://nn.cs.utexas.edu/keyword?gomez:gecco03. In Proceedings of the genetic and evolutionary computation conference (pp. 2084–2095). San Francisco: Morgan Kaufmann.
Gomez, F., Schmidhuber, J., & Miikkulainen, R. (2008). Accelerated neural evolution through cooperatively coevolved syn-apses http://nn.cs.utexas.edu/keyword?gomez:jmlr08. Journal of Machine Learning Research, 9, 937–965.
Gruau, F., & Whitley, D. (1993). Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect. Evolutionary Computation, 1, 213–233.
Igel, C. (2003). Neuroevolution for reinforcement learning using evolution strategies http://www.neuroinformatik.ruhr-uni-bochum.de/ini/PEOPLE/igel/NfRLUES.pdf. In R. Sarker, R. Reynolds, H. Abbass, K. C. Tan, B. McKay, D. Essam, & T. Gedeon, (Eds.), Proceedings of the 2003 congress on evolutionary computation (pp. 2588–2595). Piscataway, NJ: IEEE Press.
Keinan, A., Sandbank, B., Hilgetag, C. C., Meilijson, I., & Ruppin, E. (2006). Axiomatic scalable neurocontroller analysis via the Shapley value. Artificial Life, 12, 333–352.
Liu, Y., Yao, X., & Higuchi, T. (2000). Evolutionary ensembles with negative correlation learning. IEEE Transactions on Evolutionary Computation, 4, 380–387.
Miikkulainen, R., Bryant, B. D., Cornelius, R., Karpov, I. V., Stanley, K. O., & Yong, C. H. (2006). Compu-tational intelligence in games http://nn.cs.utexas.edu/keyword?miikkulainen:cigames06. In G. Y. Yen & D. B. Fogel (Eds.), Computational intelligence: Principles and practice (155–191). Piscataway, NJ: IEEE Computational Intelligence Society.
Moriarty, D. E., Schultz, A. C., & Grefenstette, J. J. (1999). Evolutionary algorithms for reinforcement learning. Journal of Artificial Intelligence Research, 11, 199–229.
Nolfi, S., & Floreano, D. (2000). Evolutionary robotics. Cambridge, MA: MIT Press.
Potter, M. A., & Jong, K. A. D. (2000). Cooperative coevolution: An architecture for evolving coadapted subcomponents http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=retrieve&db=pubmed&dopt=abstract&list_uids=10753229. Evolutionary Computation, 8, 1–29.
Schaffer, J. D., Whitley, D., & Eshelman, L. J. (1992). Combinations of genetic algorithms and neural networks: A survey of the state of the art. In D. Whitley & J. Schaffer (Eds.), Proceedings of the international workshop on combinations of genetic algorithms and neural networks (pp. 1–37). Los Alamitos, CA: IEEE Computer Society Press.
Stanley, K. O., & Miikkulainen, R. (2003). A taxonomy for artificial embryogeny http://nn.cs.utexas.edu/keyword?stanley:alife03. Artificial Life, 9, 93–130.
Stanley, K. O., & Miikkulainen, R. (2004). Competitive coevolution through evolutionary complexification http://nn.cs.utexas.edu/keyword?stanley:jair04. Journal of Artificial Intelligence Research, 21, 63–100.
Togelius, J., & Lucas, S. M. (2006). Evolving robust and specialized car racing skills http://algoval.essex.ac.uk/rep/games/Togelius2006Evolving.pdf. In IEEE congress on evolutionary computation (pp. 1187–1194). Piscataway, NJ: IEEE.
Werner, G. M., & Dyer, M. G. (1992). Evolution of communication in artificial organisms. In C. G. Langton, C. Taylor, J. D. Farmer, & S. Rasmussen (Eds.) Proceedings of the workshop on artificial life (ALIFE ’90) (pp. 659–687). Reading, MA: Addison- Wesley.
Yao, X. (1999). Evolving artificial neural networks. Proceedings of the IEEE, 87(9), 1423–1447.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
Miikkulainen, R. (2011). Neuroevolution. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_589
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_589
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30768-8
Online ISBN: 978-0-387-30164-8
eBook Packages: Computer ScienceReference Module Computer Science and Engineering